24小时热门版块排行榜    

查看: 300  |  回复: 3
【有奖交流】积极回复本帖子,参与交流,就有机会分得作者 yaoshunbo 的 7 个金币 ,回帖就立即获得 1 个金币,每人有 1 次机会

yaoshunbo

木虫 (小有名气)


[交流] 欢迎引用

摘要:Hybrid electric vehicles can achieve better fuel economy than conventional vehicles by utilizing multiple power sources. While these power sources have been controlled by rule-based or optimization-based control algorithms, recent studies have shown that machine learning-based con trol algorithms such as online Deep Reinforcement Learning (DRL) can effectively control the power sources as well. However, the optimization and training processes for the online DRL-based pow ertrain control strategy can be very time and resource intensive. In this paper, a new offline–online hybrid DRL strategy is presented where offline vehicle data are exploited to build an initial model and an online learning algorithm explores a new control policy to further improve the fuel economy. In this manner, it is expected that the agent can learn an environment consisting of the vehicle dynamics in a given driving condition more quickly compared to the online algorithms, which learn the optimal control policy by interacting with the vehicle model from zero initial knowledge. By incorporating a priori offline knowledge, the simulation results show that the proposed approach not only accelerates the learning process and makes the learning process more stable, but also leads to a better fuel economy compared to online only learning algorithms.

论文:With the advancements of data science, machine learning has become a vital tool for improving decision making by using raw data and information as input. Significant results can be  seen by using different machine learning techniques in various real-world domains, such as cybersecurity systems, engineering, healthcare, e-commerce, agriculture, etc. [1]
[1] Yao, Z.; Yoon, H.-S.; Hong, Y.-K. Control of Hybrid Electric Vehicle Powertrain Using Offline-Online Hybrid Reinforcement Learning. Energies 2023, 16, 652. https://doi.org/10.3390/en16020652
回复此楼

» 猜你喜欢

» 抢金币啦!回帖就可以得到:

查看全部散金贴

已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖
简单回复
newind2楼
2023-02-28 14:53   回复  
yaoshunbo(金币+1): 谢谢参与
发自小木虫Android客户端
tzynew3楼
2023-02-28 21:46   回复  
yaoshunbo(金币+1): 谢谢参与
2023-02-28 21:54   回复  
yaoshunbo(金币+1): 谢谢参与
相关版块跳转 我要订阅楼主 yaoshunbo 的主题更新
提示: 如果您在30分钟内回复过其他散金贴,则可能无法领取此贴金币
最具人气热帖推荐 [查看全部] 作者 回/看 最后发表
[硕博家园] 每到中夜,情难自抑 +36 sioc-sunj 2024-05-28 60/3000 2024-06-03 02:18 by 梨花儿
[基金申请] 2024杰青和万人领军什么时候会评 +5 墨香琴韵 2024-06-02 5/250 2024-06-02 19:31 by xiaqiu
[基金申请] 入职高校3年发表10+SCI,尽人事听天命 +33 kaoyan250 2024-05-27 48/2400 2024-06-02 19:17 by kaoyan250
[基金申请] +5 河马の史诗 2024-06-02 5/250 2024-06-02 19:05 by 328838485
[教师之家] 选择 +8 459582015 2024-05-31 11/550 2024-06-02 18:30 by auvauv
[基金申请] 九部门发文:不得将专利授权数量作为人才评价、项目评审、职称评定、高校评价等的条件 +17 sjtu2012 2024-05-28 21/1050 2024-06-02 13:43 by 欢乐颂叶蓁
[教师之家] 在大地上我们只过一生---看完我的阿勒泰上头了好几天,完结那天晚上几乎失眠 +11 瞬息宇宙 2024-05-27 13/650 2024-06-01 22:15 by otani
[考研] 研0二导师分到新来的博士后靠谱吗 +7 sone9 2024-05-31 7/350 2024-06-01 19:10 by 梦燕园
[教师之家] 研究生在毕业答辩时挂了,遗憾 +10 spacr2022 2024-05-27 13/650 2024-06-01 17:45 by keyaner23
[论文投稿] 求Sci期刊推荐 10+4 甄小鱼 2024-05-30 7/350 2024-06-01 10:41 by bobvan
[基金申请] 博后特别资助状态变化 +24 随梦而飞2017 2024-05-30 35/1750 2024-06-01 10:10 by 青岛阳仔
[考博] 申博求助?本硕双非一篇三区和四区去985工科非天坑专业有没有希望? +4 LYS1200 2024-05-29 6/300 2024-06-01 08:50 by 学术渣渣神
[论文投稿] 纠结选哪一个期刊,电化学领域 50+8 Freya163 2024-05-28 10/500 2024-05-31 15:09 by wzykobe
[高分子] MMA预聚体光固化发雾问题求助 +3 惠亚金总 2024-05-29 10/500 2024-05-31 14:59 by 惠亚金总
[文学芳草园] 对对子啊 +5 天若孤独 2024-05-29 7/350 2024-05-31 09:00 by wjykycg
[论文投稿] 《控制理论与应用》期刊收版面费吗? +4 ygj2015 2024-05-29 4/200 2024-05-30 06:59 by nono2009
[博后之家] 2024公派博后申请 +4 326lhpqk 2024-05-27 5/250 2024-05-29 20:03 by @古月胡
[论文投稿] 高手朋友推荐比较容易投稿和录用的SCI期刊,不投稿收费SC,对分区没有要求 5+3 xintangren 2024-05-28 4/200 2024-05-29 10:46 by xintangren
[论文投稿] EI学报,一审返修后,为啥不再送审,直接终审中? +4 qweasd12345 2024-05-27 6/300 2024-05-29 00:02 by dut_ameng
[基金申请] E10开始送了,希望有好运 +5 sail 2024-05-27 5/250 2024-05-28 18:36 by 芝小芝
信息提示
请填处理意见